A Hybrid Deep Learning and Machine Learning-Based Approach to Classify Defects in Hot Rolled Steel Strips for Smart Manufacturing

Smart manufacturing is a process that optimizes factory performance and production quality by utilizing various technologies including the Internet of Things(IoT)and artificial intelligence(AI).Quality control is an important part of today’s smart manufacturing process,effectively reducing costs and enhancing operational efficiency.As technology in the industry becomes more advanced,identifying and classifying defects has become an essential element in ensuring the quality of products during the manufacturing process.In this study,we introduce a CNN model for classifying defects on hot-rolled steel strip surfaces using hybrid deep learning techniques,incorporating a global average pooling(GAP)layer and a machine learning-based SVM classifier,with the aim of enhancing accuracy.Initially,features are extracted by the VGG19 convolutional block.Then,after processing through the GAP layer,the extracted features are fed to the SVM classifier for classification.For this purpose,we collected images from publicly available datasets,including the Xsteel surface defect dataset(XSDD)and the NEU surface defect(NEU-CLS)datasets,and we employed offline data augmentation techniques to balance and increase the size of the datasets.The outcome of experiments shows that the proposed methodology achieves the highest metrics score,with 99.79%accuracy,99.80%precision,99.79%recall,and a 99.79%F1-score for the NEU-CLS dataset.Similarly,it achieves 99.64%accuracy,99.65%precision,99.63%recall,and a 99.64%F1-score for the XSDD dataset.A comparison of the proposed methodology to the most recent study showed that it achieved superior results as compared to the other studies.

An Adaptive Bandwidth Allocation for Energy Efficient Wireless Communication Systems

In this paper, an energy efficient bandwidth allocation scheme is proposed for wireless communication systems. An optimal bandwidth expansion（OBE） scheme is proposed to assign the available system bandwidth for users. When the system bandwidth does not reach the full load, the remaining bandwidth can be energy-efficiently assigned to the other users. Simulation results show that the energy efficiency of the proposed OBE scheme outperforms the traditional same bandwidth expansion（SBE） scheme. Thus, the proposed OBE can effectively assign the system bandwidth and improve energy efficiency.

An effective communication and computation model based on a hybridgraph-deeplearning approach for SIoT

Social Edge Service(SES)is an emerging mechanism in the Social Internet of Things(SIoT)orchestration for effective user-centric reliable communication and computation.The services are affected by active and/or passive attacks such as replay attacks,message tampering because of sharing the same spectrum,as well as inadequate trust measurement methods among intelligent devices(roadside units,mobile edge devices,servers)during computing and content-sharing.These issues lead to computation and communication overhead of servers and computation nodes.To address this issue,we propose the HybridgrAph-Deep-learning(HAD)approach in two stages for secure communication and computation.First,the Adaptive Trust Weight(ATW)model with relation-based feedback fusion analysis to estimate the fitness-priority of every node based on directed graph theory to detect malicious nodes and reduce computation and communication overhead.Second,a Quotient User-centric Coeval-Learning(QUCL)mechanism to formulate secure channel selection,and Nash equilibrium method for optimizing the communication to share data over edge devices.The simulation results confirm that our proposed approach has achieved effective communication and computation performance,and enhanced Social Edge Services(SES)reliability than state-of-the-art approaches.

MDTCNet:Multi-Task Classifications Network and TCNN for Direction of Arrival Estimation

The direction-of-arrival(DoA) estimation is one of the hot research areas in signal processing. To overcome the DoA estimation challenge without the prior information about signal sources number and multipath number in millimeter wave system,the multi-task deep residual shrinkage network(MTDRSN) and transfer learning-based convolutional neural network(TCNN), namely MDTCNet, are proposed. The sampling covariance matrix based on the received signal is used as the input to the proposed network. A DRSN-based multi-task classifications model is first introduced to estimate signal sources number and multipath number simultaneously. Then, the DoAs with multi-signal and multipath are estimated by the regression model. The proposed CNN is applied for DoAs estimation with the predicted number of signal sources and paths. Furthermore, the modelbased transfer learning is also introduced into the regression model. The TCNN inherits the partial network parameters of the already formed optimization model obtained by the CNN. A series of experimental results show that the MDTCNet-based DoAs estimation method can accurately predict the signal sources number and multipath number under a range of signal-to-noise ratios. Remarkably, the proposed method achieves the lower root mean square error compared with some existing deep learning-based and traditional methods.

Randomization Strategies in Image Steganography Techniques:A Review

Image steganography is one of the prominent technologies in data hiding standards.Steganographic system performance mostly depends on the embedding strategy.Its goal is to embed strictly confidential information into images without causing perceptible changes in the original image.The randomization strategies in data embedding techniques may utilize random domains,pixels,or region-of-interest for concealing secrets into a cover image,preventing information from being discovered by an attacker.The implementation of an appropriate embedding technique can achieve a fair balance between embedding capability and stego image imperceptibility,but it is challenging.A systematic approach is used with a standard methodology to carry out this study.This review concentrates on the critical examination of several embedding strategies,incorporating experimental results with state-of-the-art methods emphasizing the robustness,security,payload capacity,and visual quality metrics of the stego images.The fundamental ideas of steganography are presented in this work,along with a unique viewpoint that sets it apart from previous works by highlighting research gaps,important problems,and difficulties.Additionally,it offers a discussion of suggested directions for future study to advance and investigate uncharted territory in image steganography.

Learning-based user association and dynamic resource allocation in multi-connectivity enabled unmanned aerial vehicle networks

Unmanned Aerial Vehicles(UAvs)as aerial base stations to provide communication services for ground users is a flexible and cost-effective paradigm in B5G.Besides,dynamic resource allocation and multi-connectivity can be adopted to further harness the potentials of UAVs in improving communication capacity,in such situations such that the interference among users becomes a pivotal disincentive requiring effective solutions.To this end,we investigate the Joint UAV-User Association,Channel Allocation,and transmission Power Control(J-UACAPC)problem in a multi-connectivity-enabled UAV network with constrained backhaul links,where each UAV can determine the reusable channels and transmission power to serve the selected ground users.The goal was to mitigate co-channel interference while maximizing long-term system utility.The problem was modeled as a cooperative stochastic game with hybrid discrete-continuous action space.A Multi-Agent Hybrid Deep Reinforcement Learning(MAHDRL)algorithm was proposed to address this problem.Extensive simulation results demonstrated the effectiveness of the proposed algorithm and showed that it has a higher system utility than the baseline methods.

Effect of hydrogen fluoride and magnesium oxide on AZ31 Mg alloy/carbon fiber-reinforced plastic composite by thermal laser joining technique

Although hydrofluoric acid(HF)surface treatment is known to enhance the joining of metals with polymers,there is limited information on its effect on the joining of AZ31 alloy and carbon-fiber-reinforced plastics(CFRPs)through laser-assisted metal and plastic direct joining(LAMP).This study uses the LAMP technique to produce AZ31-CFRP joints.The joining process involves as-received AZ31,HFpretreated AZ31,and thermally oxidized HF-pretreated AZ31 alloy sheets.Furthermore,the bonding strength of joints prepared with thermally oxidized AZ31 alloy sheets is examined to ascertain the combined effect of HF treatment and thermal oxidation on bonding strength.The microstructures,surface chemical interactions,and mechanical performances of joints are investigated under tensile shear loading.Various factors,such as bubble formation,CFRP resin decomposition,and mechanical interlocking considerably affect joint strength.Additionally,surface chemical interactions between the active species on metal parts and the polar amide along with carbonyl groups of polymer play a significant role in improving joint strength.Joints prepared with surface-pretreated AZ31 alloy sheets show significant improvements in bonding strength.

A Comprehensive Survey on Federated Learning in the Healthcare Area: Concept and Applications

Federated learning is an innovative machine learning technique that deals with centralized data storage issues while maintaining privacy and security.It involves constructing machine learning models using datasets spread across several data centers,including medical facilities,clinical research facilities,Internet of Things devices,and even mobile devices.The main goal of federated learning is to improve robust models that benefit from the collective knowledge of these disparate datasets without centralizing sensitive information,reducing the risk of data loss,privacy breaches,or data exposure.The application of federated learning in the healthcare industry holds significant promise due to the wealth of data generated from various sources,such as patient records,medical imaging,wearable devices,and clinical research surveys.This research conducts a systematic evaluation and highlights essential issues for the selection and implementation of federated learning approaches in healthcare.It evaluates the effectiveness of federated learning strategies in the field of healthcare.It offers a systematic analysis of federated learning in the healthcare domain,encompassing the evaluation metrics employed.In addition,this study highlights the increasing interest in federated learning applications in healthcare among scholars and provides foundations for further studies.

Determination of the best materials for development and designing product using a multi-criteria decision-making

Purpose–Material selection,driven by wide and often conflicting objectives,is an important,sometimes difficult problem in material engineering.In this context,multi-criteria decision-making(MCDM)methodologies are effective.An approach of MCDM is needed to cater to criteria of material assortment simultaneously.More firms are now concerned about increasing their productivity using mathematical tools.To occupy a gap in the previous literature this research recommends an integrated MCDM and mathematical Bi-objective model for the selection of material.In addition,by using the Technique for Order Preference by Similarity to Ideal Solution(TOPSIS),the inherent ambiguities of decision-makers in paired evaluations are considered in this research.It goes on to construct a mathematical bi-objective model for determining the best item to purchase.Design/methodology/approach–The entropy perspective is implemented in this paper to evaluate the weight parameters,while the TOPSIS technique is used to determine the best and worst intermediate pipe materials for automotive exhaust system.The intermediate pipes are used to join the components of the exhaust systems.The materials usually used to manufacture intermediate pipe are SUS 436LM,SUS 430,SUS 304,SUS 436L,SUH 409 L,SUS 441 L and SUS 439L.These seven materials are evaluated based on tensile strength(TS),hardness(H),elongation(E),yield strength(YS)and cost(C).A hybrid methodology combining entropy-based criteria weighting,with the TOPSIS for alternative ranking,is pursued to identify the optimal design material for an engineered application in this paper.This study aims to help while filling the information gap in selecting the most suitable material for use in the exhaust intermediate pipes.After that,the authors searched for and considered eight materials and evaluated them on the following five criteria:(1)TS,(2)YS,(3)H,(4)E and(5)C.The first two criteria have been chosen because they can have a lot of influence on the behavior of the exhaust intermediate pipes,on their performance and on the cost.In this structure,the weights of the criteria are calculated objectively through the entropy method in order to have an unbiased assessment.This essentially measures the quantity of information each criterion contribution,indicating the relative importance of these criteria better.Subsequently,the materials were ranked using the TOPSIS method in terms of their relative performance by measuring each material from an ideal solution to determine the best alternative.The results show that SUS 309,SUS 432L and SUS 436 LM are the first three materials that the exhaust intermediate pipe optimal design should consider.Findings–The material matrix of the decision presented in Table 3 was normalized through Equation 5,as shown in Table 5,and the matrix was multiplied with weighting criteriaß_j.The obtained weighted normalized matrix V_ij is presented in Table 6.However,the ideal,worst and best value was ascertained by employing Equation 7.This study is based on the selection of material for the development of intermediate pipe using MCDM,and it involves four basic stages,i.e.method of translation criteria,screening process,method of ranking and search for methods.The selection was done through the TOPSIS method,and the criteria weight was obtained by the entropy method.The result showed that the top three materials are SUS 309,SUS 432L and SUS 436 LM,respectively.For the future work,it is suggested to select more alternatives and criteria.The comparison can also be done by using different MCDM techniques like and Choice Expressing Reality(ELECTRE),Decision-Making Trial and Evaluation Laboratory(DEMATEL)and Preference Ranking Organization Method for Enrichment Evaluation(PROMETHEE).Originality/value–The results provide important conclusions for material selection in this targeted application,verifying the employment of mutual entropy-TOPSIS methodology for a series of difficult engineering decisions in material engineering concepts that combine superior capacity with better performance as well as cost-efficiency in various engineering design.

Steel Surface Defect Recognition in Smart Manufacturing Using Deep Ensemble Transfer Learning-Based Techniques

Smart manufacturing and Industry 4.0 are transforming traditional manufacturing processes by utilizing innovative technologies such as the artificial intelligence(AI)and internet of things(IoT)to enhance efficiency,reduce costs,and ensure product quality.In light of the recent advancement of Industry 4.0,identifying defects has become important for ensuring the quality of products during the manufacturing process.In this research,we present an ensemble methodology for accurately classifying hot rolled steel surface defects by combining the strengths of four pre-trained convolutional neural network(CNN)architectures:VGG16,VGG19,Xception,and Mobile-Net V2,compensating for their individual weaknesses.We evaluated our methodology on the Xsteel surface defect dataset(XSDD),which comprises seven different classes.The ensemble methodology integrated the predictions of individual models through two methods:model averaging and weighted averaging.Our evaluation showed that the model averaging ensemble achieved an accuracy of 98.89%,a recall of 98.92%,a precision of 99.05%,and an F1-score of 98.97%,while the weighted averaging ensemble reached an accuracy of 99.72%,a recall of 99.74%,a precision of 99.67%,and an F1-score of 99.70%.The proposed weighted averaging ensemble model outperformed the model averaging method and the individual models in detecting defects in terms of accuracy,recall,precision,and F1-score.Comparative analysis with recent studies also showed the superior performance of our methodology.

Radar emitter signal recognition based on multi-scale wavelet entropy and feature weighting

In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio(SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than-4 d B, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.

NEAR-FIELD SOURCE LOCALIZATION METHOD AND APPLICATION USING THE TIME REVERSAL MIRROR TECHNIQUE

In order to develop the acoustic keyboard for Personal Computer(PC),it is necessary to seek high-precision near-field source localization algorithm for identifying the keyboard characters.First of all,the focusing property of Time Reversal Mirror(TRM) is introduced,and then a mathe-matical model of microphone array receiving typing sound is established according to the realization of acoustic keyboard from which the TRM localization algorithm is carried out.The results through computer simulation show that the localization Root Mean Square Error(RMSE) performance of the algorithm can reach 10-3,which demonstrates that the algorithm possesses a high accuracy for the actual near-field acoustic source localization,with potential of developing the computer acoustic keyboard.Furthermore,for the purpose of testing its effect on actual near-field source localization,we organize three experiments for acoustic keyboard characters localization.The experiment results show that the positioning error of TRM algorithm is less than 1 cm within a provided acoustic keyboard region.This will provide theoretical guidance for the further research of computer acoustic keyboard.

An adaptive fuzzy filter for coding artifacts removal in video and image

This paper proposes a new adaptive post-filtering algorithm to remove coding artifacts in block-based video coder. The proposed method concentrates on blocking and ringing artifacts removal. For de-blocking, the blocking strength is identified to determine the filtering range, and the maximum quantization parameter of the image is used to adapt the 1D fuzzy filter. For de-ringing, besides the edge detection, a complementary ringing detection method is proposed to locate the neglected ringing blocks, and the gradient threshold is adopted to adjust the parameter of 2D fuzzy filter. Experiments are performed on the MPEG-4 sequences. Compared with other methods, the proposed one achieves better detail preservation and artifacts removal performance with lower computational cost.

State estimation for neural neutral-type networks with mixed time-varying delays and Markovian jumping parameters

This paper is concerned with a delay-dependent state estimator for neutral-type neural networks with mixed timevarying delays and Markovian jumping parameters.The addressed neural networks have a finite number of modes,and the modes may jump from one to another according to a Markov process.By construction of a suitable Lyapunov-Krasovskii functional,a delay-dependent condition is developed to estimate the neuron states through available output measurements such that the estimation error system is globally asymptotically stable in a mean square.The criterion is formulated in terms of a set of linear matrix inequalities（LMIs）,which can be checked efficiently by use of some standard numerical packages.

Vehicle Positioning Based on Optical Camera Communication in V2I Environments

Demand for precise vehicle positioning(VP)increases as autonomous vehicles have recently been drawing attention.This paper proposes a scheme for positioning vehicles on the move based on optical camera communication(OCC)technology in the vehicle-to-infrastructure(V2I)environment.Light-emitting diode(LED)streetlights and vehicle cameras are used as transmitters and receivers respectively.Regions of streetlights are detected and traced by examining images that are obtained from cameras of vehicles.Then,a scheme for analyzing visible light data extracted from the images is proposed.The proposed vehicle positioning scheme uses information on angles between vectors that are formed under the collinearity conditions between the absolute coordinates of at least three received streetlights,and the coordinates of an image sensor.The experiments are performed under stationary state and moving state at a speed of 5 and 20 km/h.To verify the reliability of the proposed scheme,a comparison is made between the actual and estimated location of the camera in the stationary state.In addition,the path of a moving vehicle and the estimated path of the vehicle are compared to check the performance of the scheme.The performance of the proposed technique is analyzed and experimental demonstration confirms that the proposed OCC-based VP scheme achieves positioning accuracy of under 1 m.

Machine learning-based zero-touch network and service management:a survey

The exponential growth of mobile applications and services during the last years has challenged the existing network infrastructures.Consequently,the arrival of multiple management solutions to cope with this explosion along the end-to-end network chain has increased the complexity in the coordinated orchestration of different segments composing the whole infrastructure.The Zero-touch Network and Service Management(ZSM)concept has recently emerged to automatically orchestrate and manage network resources while assuring the Quality of Experience(QoE)demanded by users.Machine Learning(ML)is one of the key enabling technologies that many ZSM frameworks are adopting to bring intelligent decision making to the network management system.This paper presents a comprehensive survey of the state-of-the-art application of ML-based techniques to improve ZSM performance.To this end,the main related standardization activities and the aligned international projects and research efforts are deeply examined.From this dissection,the skyrocketing growth of the ZSM paradigm can be observed.Concretely,different standardization bodies have already designed reference architectures to set the foundations of novel automatic network management functions and resource orchestration.Aligned with these advances,diverse ML techniques are being currently exploited to build further ZSM developments in different aspects,including multi-tenancy management,traffic monitoring,and architecture coordination,among others.However,different challenges,such as the complexity,scalability,and security of ML mechanisms,are also identified,and future research guidelines are provided to accomplish a firm development of the ZSM ecosystem.

Dark channel prior based blurred image restoration method using total variation and morphology

The blurred image restoration method can dramatically highlight the image details and enhance the global contrast, which is of benefit to improvement of the visual effect during practical ap- plications. This paper is based on the dark channel prior principle and aims at the prior information absent blurred image degradation situation. A lot of improvements have been made to estimate the transmission map of blurred images. Since the dark channel prior principle can effectively restore the blurred image at the cost of a large amount of computation, the total variation （TV） and image morphology transform （specifically top-hat transform and bottom- hat transform） have been introduced into the improved method. Compared with original transmission map estimation methods, the proposed method features both simplicity and accuracy. The es- timated transmission map together with the element can restore the image. Simulation results show that this method could inhibit the ill-posed problem during image restoration, meanwhile it can greatly improve the image quality and definition.

Brain Tumor Detection and Segmentation Using RCNN

Brain tumors are considered as most fatal cancers.To reduce the risk of death,early identification of the disease is required.One of the best available methods to evaluate brain tumors is Magnetic resonance Images(MRI).Brain tumor detection and segmentation are tough as brain tumors may vary in size,shape,and location.That makes manual detection of brain tumors by exploring MRI a tedious job for radiologists and doctors’.So an automated brain tumor detection and segmentation is required.This work suggests a Region-based Convolution Neural Network(RCNN)approach for automated brain tumor identification and segmentation using MR images,which helps solve the difficulties of brain tumor identification efficiently and accurately.Our methodology is based on the accurate and efficient selection of tumorous areas.That reduces computational complexity and time.We have validated the designed experimental setup on a standard dataset,BraTS 2020.We used binary evaluation matrices based on Dice Similarity Coefficient(DSC)and Mean Average Precision(mAP).The segmentation results are compared with state-of-the-art methodologies to demonstrate the effectiveness of the proposed method.The suggested approach attained an averageDSC of 0.92 andmAP 0.92 for 10 patients,while on the whole dataset,the scores are DSC 0.89 and mAP 0.90.The following results clearly show the performance efficiency of the proposed methodology.

Analysis and Modeling of Propagation in Tunnel at 3.7 and 28 GHz

In present-day society,train tunnels are extensively used as a means of transportation.Therefore,to ensure safety,streamlined train operations,and uninterrupted internet access inside train tunnels,reliable wave propagation modeling is required.We have experimented and measured wave propagation models in a 1674 m long straight train tunnel in South Korea.The measured path loss and the received signal strength were modeled with the Close-In(CI),Floating intercept(FI),CI model with a frequency-weighted path loss exponent(CIF),and alpha-beta-gamma(ABG)models,where the model parameters were determined using minimum mean square error(MMSE)methods.The measured and the CI,FI,CIF,and ABG modelderived path loss was plotted in graphs,and the model closest to the measured path loss was identified through investigation.Based on the measured results,it was observed that every model had a comparatively lower(n<2)path loss exponent(PLE)inside the tunnel.We also determined the path loss component’s possible deviation(shadow factor)through a Gaussian distribution considering zero mean and standard deviation calculations of random error variables.The FI model outperformed all the examined models as it yielded a path loss closer to the measured datasets,as well as a minimum standard deviation of the shadow factor.

Collision Observation-Based Optimization of Low-Power and Lossy IoT Network Using Reinforcement Learning

The Internet of Things(IoT)has numerous applications in every domain,e.g.,smart cities to provide intelligent services to sustainable cities.The next-generation of IoT networks is expected to be densely deployed in a resource-constrained and lossy environment.The densely deployed nodes producing radically heterogeneous traffic pattern causes congestion and collision in the network.At the medium access control(MAC)layer,mitigating channel collision is still one of the main challenges of future IoT networks.Similarly,the standardized network layer uses a ranking mechanism based on hop-counts and expected transmission counts(ETX),which often does not adapt to the dynamic and lossy environment and impact performance.The ranking mechanism also requires large control overheads to update rank information.The resource-constrained IoT devices operating in a low-power and lossy network(LLN)environment need an efficient solution to handle these problems.Reinforcement learning(RL)algorithms like Q-learning are recently utilized to solve learning problems in LLNs devices like sensors.Thus,in this paper,an RL-based optimization of dense LLN IoT devices with heavy heterogeneous traffic is devised.The proposed protocol learns the collision information from the MAC layer and makes an intelligent decision at the network layer.The proposed protocol also enhances the operation of the trickle timer algorithm.A Q-learning model is employed to adaptively learn the channel collision probability and network layer ranking states with accumulated reward function.Based on a simulation using Contiki 3.0 Cooja,the proposed intelligent scheme achieves a lower packet loss ratio,improves throughput,produces lower control overheads,and consumes less energy than other state-of-the-art mechanisms.